SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure

• URL: http://arxiv.org/abs/2607.02814v1
• Date: Thu, 02 Jul 2026 23:03:15 GMT
• Title: SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure
• Abstract summary: SovereignNegotiation-Bench is a trace-level benchmark for delegated personal-agent negotiation under private utilities.<n>We report an artifact-backed validation over 240 scenarios, 4 model families, 13,440 frozen-prompt live trajectories, 61,135 parsed action rows, and a blinded 3-annotator audit over 300 items.<n>The strongest agreement-maximizing baseline achieves the highest agreement rate but low user utility and high privacy/consent risk.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating support disputes, requesting refunds, changing subscriptions, and negotiating deadlines or reimbursements. Existing negotiation benchmarks emphasize agreement, surplus, or strategic competence, but a user-owned agent can reach an agreement while harming the user through privacy leakage, consent violation, unsupported advocacy, over-concession, failed escalation, or poor auditability. We introduce SovereignNegotiation-Bench, a trace-level multi-turn benchmark for delegated personal-agent negotiation under private utilities, disclosure constraints, evidence requirements, and institutional asymmetry. The benchmark separates agent-visible observable state from evaluator-only labels and evaluates agreement success jointly with user utility, privacy, consent, evidence grounding, concession discipline, escalation, and auditability. We report an artifact-backed validation over 240 scenarios, 4 model families, 14 baselines, 13,440 frozen-prompt live trajectories, 61,135 parsed action rows, and a blinded 3-annotator audit over 300 items. The strongest agreement-maximizing baseline achieves the highest agreement rate but low user utility and high privacy/consent risk; FullSovereign does not maximize agreement, but obtains the best sovereign negotiation score by preserving utility, minimizing leakage, grounding claims, and reducing unauthorized commitments. The results show that agreement success is insufficient for user-owned negotiation agents.

Related papers

• Sharding Prevents LLM Oversight Failures and Adversarial Exploitation [45.380649793616705]
  Sharding partitions requirements into smaller groups, assigns each group to a separate call, and aggregates the verdicts.<n>We find that a sharded weaker judge can outperform a more capable holistic judge and match that judge even when the latter receives the panel's full budget.
  arXiv  Detail & Related papers  (2026-08-05T18:21:21Z)
• Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies [0.0]
  This paper investigates behavioral differential privacy in multi-round negotiation protocols.<n>We design an adaptive negotiation policy that jointly guarantees $(varepsilon, )$-differential privacy.<n>Our mechanism reduces adversarial inference accuracy by 43-50% while maintaining a negotiation success rate and utility above 90%.
  arXiv  Detail & Related papers  (2026-07-07T21:22:28Z)
• SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints [0.0]
  SovereignPA-Bench is an executable benchmark for evaluating user-owned personal agents.<n>We evaluate 120 sovereignty stress scenarios across 4 model families and 8 policy baselines.
  arXiv  Detail & Related papers  (2026-07-06T17:39:05Z)
• What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents [2.8340200313563773]
  Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.<n>Agents trained under human-feedback objectives develop a structural tendency to proceed even when they lack the inputs, evidence, or authorization to act safely.<n>We introduce a three-gap taxonomy of abstention-warranted scenarios, covering specification gaps where required information is absent, verification gaps where world state cannot be confirmed, and authority gaps where explicit authorization has not been given.
  arXiv  Detail & Related papers  (2026-06-01T23:52:56Z)
• TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate [34.67393151003599]
  Negotiation is a canonical testbed for agentic language models.<n>Unlike math or code, it has no intrinsic verifier.<n>We introduce Terms-Bench, a Bayesian-game framework that makes the environment itself the verifier.
  arXiv  Detail & Related papers  (2026-05-13T06:22:50Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization [4.511923587827302]
  We design a human-AI negotiation case study in a realistic property rental scenario.<n> empirical findings show that performance stays stable up to three issues but declines as additional issues increase cognitive load.<n>We introduce a novel uncertainty-based visualization driven by Bayesian estimation of agreement probability.
  arXiv  Detail & Related papers  (2026-03-24T03:49:21Z)
• Fairness Dynamics in Digital Economy Platforms with Biased Ratings [50.29721091981893]
  We study how digital platforms can perpetuate or counteract rating-based discrimination.<n>Our results demonstrate a fundamental trade-off between user experience and fairness.<n>Our results also provide evidence that intervening by tuning the demographics of the search results is a highly effective way of reducing unfairness.
  arXiv  Detail & Related papers  (2026-02-18T18:41:16Z)
• From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making [0.0]
  Low-friction assistants can become sycophantic, baking in implicit assumptions and pushing verification costs onto experts.<n>We argue reliable human-AI partnership requires a shift from answer generation to collaborative premise governance.
  arXiv  Detail & Related papers  (2026-02-02T17:42:54Z)
• EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation [66.09161596959771]
  Small language models (SLMs) offer a practical alternative, but suffer from a significant performance gap compared to large language models (LLMs)<n>This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas.<n>We show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size.
  arXiv  Detail & Related papers  (2025-11-05T11:25:07Z)
• MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation [61.92403071137653]
  Existing privacy benchmarks only focus on simplistic, single-turn interactions where private information can be trivially omitted without affecting task outcomes.<n>We introduce MAGPIE, a novel benchmark designed to evaluate privacy understanding and preservation in multi-agent collaborative, non-adversarial scenarios.<n>Our evaluation reveals that state-of-the-art agents, including GPT-5 and Gemini 2.5-Pro, exhibit significant privacy leakage.
  arXiv  Detail & Related papers  (2025-10-16T23:12:12Z)
• Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement [49.15348173246146]
  We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncritically rely on model preferences for pairwise evaluation. We then show that under this selective evaluation framework, human agreement can be provably guaranteed.
  arXiv  Detail & Related papers  (2024-07-25T20:04:59Z)
• Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues [47.977032883078664]
  We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations.<n>A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes.<n>We provide rich empirical evidence to demonstrate its effectiveness in negotiations across three different negotiation topics.
  arXiv  Detail & Related papers  (2024-01-29T09:07:40Z)
• Learnable Strategies for Bilateral Agent Negotiation over Multiple Issues [6.12762193927784]
  We present a novel bilateral negotiation model that allows a self-interested agent to learn how to negotiate over multiple issues. The model relies upon interpretable strategy templates representing the tactics the agent should employ during the negotiation. It learns template parameters to maximize the average utility received over multiple negotiations, thus resulting in optimal bid acceptance and generation.
  arXiv  Detail & Related papers  (2020-09-17T13:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.